Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the word "Muslims" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to Muslims in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATA
    -0.78
     Vaugh
    -0.74
    æ©
    -0.70
     Rockefeller
    -0.69
    inventoryQuantity
    -0.68
    å§
    -0.68
    clip
    -0.67
     Hoover
    -0.65
    amina
    -0.65
     Churchill
    -0.62
    POSITIVE LOGITS
    ophobic
    1.12
    abad
    1.05
    ophobia
    1.04
    hammad
    0.97
    folk
    0.92
    istani
    0.92
    ervative
    0.82
    alam
    0.80
    majority
    0.78
    aurus
    0.77
    Act Density 0.010%

    No Known Activations